当前位置: X-MOL 学术IEEE Comput. Archit. Lett. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Characterizing and Understanding GCNs on GPU
IEEE Computer Architecture Letters ( IF 1.4 ) Pub Date : 2020-01-01 , DOI: 10.1109/lca.2020.2970395
Mingyu Yan , Zhaodong Chen , Lei Deng , Xiaochun Ye , Zhimin Zhang , Dongrui Fan , Yuan Xie

Graph convolutional neural networks (GCNs) have achieved state-of-the-art performance on graph-structured data analysis. Like traditional neural networks, training and inference of GCNs are accelerated with GPUs. Therefore, characterizing and understanding the execution pattern of GCNs on GPU is important for both software and hardware optimization. Unfortunately, to the best of our knowledge, there is no detailed characterization effort of GCN workloads on GPU. In this letter, we characterize GCN workloads at inference stage and explore GCN models on NVIDIA V100 GPU. Given the characterization and exploration, we propose several useful guidelines for both software optimization and hardware optimization for the efficient execution of GCNs on GPU.

中文翻译:

表征和理解 GPU 上的 GCN

图卷积神经网络 (GCN) 在图结构数据分析方面取得了最先进的性能。与传统的神经网络一样,GCN 的训练和推理使用 GPU 进行加速。因此,表征和理解 GCN 在 GPU 上的执行模式对于软件和硬件优化都很重要。不幸的是,据我们所知,没有对 GPU 上的 GCN 工作负载进行详细的表征工作。在这封信中,我们描述了推理阶段的 GCN 工作负载,并探索了 NVIDIA V100 GPU 上的 GCN 模型。鉴于表征和探索,我们为在 GPU 上有效执行 GCN 的软件优化和硬件优化提出了几个有用的指导方针。
更新日期:2020-01-01
down
wechat
bug